cv
This is a description of the page. You can modify it in '_pages/cv.md'. You can also change or remove the top pdf download button.
Basics
| Name | Najwa Laabid |
| Label | PhD Student |
| najwa.laabid@aalto.fi | |
| Url | https://najwalaabid.github.io |
| Summary | PhD student at Aalto University working on machine learning applied to drug discovery. |
Education
-
Espoo, Finland
Publications
-
2025 Equivariant Denoisers Cannot Copy Graphs: Align Your Graph Diffusion Models
ICLR 2025
We demonstrate that standard permutation equivariant denoisers face fundamental limitations in graph-to-graph translation tasks and propose aligning input and target graphs to break input symmetries while preserving permutation equivariance.
Skills
| Machine Learning | |
| Graph Neural Networks | |
| Diffusion Models | |
| Drug Discovery | |
| Retrosynthesis |
Languages
| English | |
| Fluent |
| French | |
| Fluent |
| Arabic | |
| Native speaker |
Interests
| Machine Learning | |
| Graph Diffusion Models | |
| Drug Discovery | |
| Retrosynthesis | |
| Generative Models |